Files changed (1) hide show
  1. README.md +113 -5
README.md CHANGED
@@ -1,4 +1,8 @@
1
  ---
 
 
 
 
2
  base_model:
3
  - DreadPoor/Heart_Stolen-8B-Model_Stock
4
  - bunnycore/Llama-3.1-8B-TitanFusion
@@ -6,11 +10,101 @@ base_model:
6
  - DreadPoor/Aspire-8B-model_stock
7
  - vicgalle/Configurable-Llama-3.1-8B-Instruct
8
  - mlabonne/Hermes-3-Llama-3.1-8B-lorablated
9
- library_name: transformers
10
- tags:
11
- - mergekit
12
- - merge
13
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  ---
15
  # merge
16
 
@@ -49,3 +143,17 @@ int8_mask: true
49
  dtype: bfloat16
50
 
51
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ library_name: transformers
3
+ tags:
4
+ - mergekit
5
+ - merge
6
  base_model:
7
  - DreadPoor/Heart_Stolen-8B-Model_Stock
8
  - bunnycore/Llama-3.1-8B-TitanFusion
 
10
  - DreadPoor/Aspire-8B-model_stock
11
  - vicgalle/Configurable-Llama-3.1-8B-Instruct
12
  - mlabonne/Hermes-3-Llama-3.1-8B-lorablated
13
+ model-index:
14
+ - name: Llama-3.1-8B-TitanFusion-v3
15
+ results:
16
+ - task:
17
+ type: text-generation
18
+ name: Text Generation
19
+ dataset:
20
+ name: IFEval (0-Shot)
21
+ type: HuggingFaceH4/ifeval
22
+ args:
23
+ num_few_shot: 0
24
+ metrics:
25
+ - type: inst_level_strict_acc and prompt_level_strict_acc
26
+ value: 48.1
27
+ name: strict accuracy
28
+ source:
29
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-v3
30
+ name: Open LLM Leaderboard
31
+ - task:
32
+ type: text-generation
33
+ name: Text Generation
34
+ dataset:
35
+ name: BBH (3-Shot)
36
+ type: BBH
37
+ args:
38
+ num_few_shot: 3
39
+ metrics:
40
+ - type: acc_norm
41
+ value: 32.07
42
+ name: normalized accuracy
43
+ source:
44
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-v3
45
+ name: Open LLM Leaderboard
46
+ - task:
47
+ type: text-generation
48
+ name: Text Generation
49
+ dataset:
50
+ name: MATH Lvl 5 (4-Shot)
51
+ type: hendrycks/competition_math
52
+ args:
53
+ num_few_shot: 4
54
+ metrics:
55
+ - type: exact_match
56
+ value: 12.99
57
+ name: exact match
58
+ source:
59
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-v3
60
+ name: Open LLM Leaderboard
61
+ - task:
62
+ type: text-generation
63
+ name: Text Generation
64
+ dataset:
65
+ name: GPQA (0-shot)
66
+ type: Idavidrein/gpqa
67
+ args:
68
+ num_few_shot: 0
69
+ metrics:
70
+ - type: acc_norm
71
+ value: 7.83
72
+ name: acc_norm
73
+ source:
74
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-v3
75
+ name: Open LLM Leaderboard
76
+ - task:
77
+ type: text-generation
78
+ name: Text Generation
79
+ dataset:
80
+ name: MuSR (0-shot)
81
+ type: TAUR-Lab/MuSR
82
+ args:
83
+ num_few_shot: 0
84
+ metrics:
85
+ - type: acc_norm
86
+ value: 11.94
87
+ name: acc_norm
88
+ source:
89
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-v3
90
+ name: Open LLM Leaderboard
91
+ - task:
92
+ type: text-generation
93
+ name: Text Generation
94
+ dataset:
95
+ name: MMLU-PRO (5-shot)
96
+ type: TIGER-Lab/MMLU-Pro
97
+ config: main
98
+ split: test
99
+ args:
100
+ num_few_shot: 5
101
+ metrics:
102
+ - type: acc
103
+ value: 31.17
104
+ name: accuracy
105
+ source:
106
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-v3
107
+ name: Open LLM Leaderboard
108
  ---
109
  # merge
110
 
 
143
  dtype: bfloat16
144
 
145
  ```
146
+
147
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
148
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_bunnycore__Llama-3.1-8B-TitanFusion-v3)
149
+
150
+ | Metric |Value|
151
+ |-------------------|----:|
152
+ |Avg. |24.02|
153
+ |IFEval (0-Shot) |48.10|
154
+ |BBH (3-Shot) |32.07|
155
+ |MATH Lvl 5 (4-Shot)|12.99|
156
+ |GPQA (0-shot) | 7.83|
157
+ |MuSR (0-shot) |11.94|
158
+ |MMLU-PRO (5-shot) |31.17|
159
+